Skip to main content

Pulkit Agrawal: Learning to Forecast and Control from Pixels

Movies Preview

texts
Pulkit Agrawal: Learning to Forecast and Control from Pixels


Published November 9, 2016
SHOW MORE


Talk by Pulkit Agrawal of UC Berkeley.  Given to the Redwood Center for Theoretical Neuroscience at UC Berkeley.

Abstract
The ability to forecast how different objects will be affected by the applied action (i.e. intuitive physics), is likely to be very useful for executing novel manipulation tasks. Similarly, the ability to forecast how humans will act in the future (i.e. intuitive behavior) can enable an agent to plan its interactions with humans. I will present results of some preliminary investigations on building intuitive models of physics (http://arxiv.org/abs/1511.07404 , https://arxiv.org/abs/1606.07419) and intuitive models of behavior (in context of water polo games) directly from visual inputs.


Language English
Collection opensource_media

comment
Reviews

There are no reviews yet. Be the first one to write a review.
SIMILAR ITEMS (based on metadata)
TED Talks
movies
eye 42
favorite 0
comment 0
TED Talks
movies
eye 55
favorite 0
comment 0
Hacker Public Radio
audio
eye 39
favorite 0
comment 0
TED Talks
movies
eye 130
favorite 0
comment 0
Community Media
data
eye 44
favorite 0
comment 0
Folkscanomy Electronics: Books on Electronics, Circuits and Processors
by Achim Zielesny
texts
eye 1,015
favorite 0
comment 0
Folkscanomy Electronics: Books on Electronics, Circuits and Processors
by Marenglen Biba, Fatos Xhafa
texts
eye 1,566
favorite 0
comment 0
Community Media
data
eye 825
favorite 0
comment 0
Scholar Work Spaces
texts
eye 2,898
favorite 1
comment 0